Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Galleon Coinbase Agentkit Readiness

ASecurity

Inspect Coinbase CDP and AgentKit wallet configuration, verify an existing account with read-only tools, and inventory exposed actions before protocol use. Use when an agent cannot find its wallet, uses the wrong Base network, or needs a scoped Coinbase capability report without creating accounts or signing.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsapi

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add galleonlabs/crypto-defi-skills --skill galleon-coinbase-agentkit-readiness --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Galleon Coinbase Agentkit Readiness?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Galleon Coinbase Agentkit Readiness
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/galleonlabs-galleon-coinbase-agentkit-readiness/badge)](https://www.skillsdirectory.com/skills/galleonlabs-galleon-coinbase-agentkit-readiness)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: galleon-coinbase-agentkit-readiness
description: Inspect Coinbase CDP and AgentKit wallet configuration, verify an existing account with read-only tools, and inventory exposed actions before protocol use. Use when an agent cannot find its wallet, uses the wrong Base network, or needs a scoped Coinbase capability report without creating accounts or signing.
license: MIT
compatibility: Portable instructions; optional offline helper uses Bun. Live recipes require an existing official provider or public HTTPS access.
metadata:
  author: Galleon Labs
  version: "0.3.0"
---

# Coinbase AgentKit readiness

Find the exact missing capability between “AgentKit installed” and “this existing account can perform the requested task.” Return a usable capability report without invoking a transaction or provisioning a wallet.

## Procedure

1. Identify the user's product: CDP API Key Wallet, AgentKit wallet provider, or email-authenticated Agentic Wallet (`awal`). They have different authentication and lifecycle behavior. A Coinbase exchange API key is not automatically a CDP wallet credential.
2. Inspect installed package versions and the existing application's selected provider, network ID, account address and exposed action list. Use [the inspection recipe](references/inspection.md). Reuse its environment without displaying values. Public market research does not require a wallet.
3. Match the expected account to its owner and the requested network. Distinguish Base mainnet `base` / 8453 from `base-sepolia` / 84532. A smart account and its owner EOA are different identities; a funded owner does not prove the smart account can pay gas.
4. Test only the reads required for the task: public chain identity, head timestamp and existing account balance; optionally authenticated retrieval of the exact existing CDP account. Record what was actually tested. Missing signer credentials do not block a public balance read.
5. Inventory action providers. Separate reads, signing, transfers, swaps, approvals and paid x402 calls. Inspect schemas/source; never infer read-only behavior from a friendly action name. Expose only the operations needed by the current application. Keep broader financial authority behind the application's explicit policy and confirmation mechanism.
6. Return the report below. If the blocker is an absent key, wrong network, unsupported action or account mismatch, name that blocker and the smallest correction. Do not “repair” readiness by creating or funding an account.

## Evidence report

```text
Product / SDK versions:
Runtime / provider:
Expected network and account:
Observed network and account:
Credential presence: set / missing (never values)
Public read: chain, block number, head time, balance and observation time
Authenticated account lookup: passed / failed / untested
Exposed action names and classifications:
Signing authority: separately configured / unknown
Next task readiness: ready for [specific read] | blocked by [specific gap]
```

## Worked cases

- “My Base balance is zero in AgentKit.” Existing provider says `base-sepolia`, user means mainnet. Report the mismatch first; use an already configured mainnet read tool for the requested balance if available. Do not fund testnet or migrate assets.
- “Is CDP ready? Keys are set.” Presence establishes local configuration only. Retrieve the expected existing account and run the scoped public read before claiming authenticated readiness. If the wallet secret is missing, public reads can still work while signing remains unverified.
- “Audit what my agent can do.” An exposed transfer action plus a balance reader means the agent has a write surface. Report exact action names and gating; do not execute a transfer as a test.

The deliverable is the scoped readiness report and, for an engineering task, a reviewable configuration correction. A tool inventory is not financial authorization. See [dated official sources](references/sources.md).

Attribution

galleonlabsgalleonlabs
View sourceMore from galleonlabs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →